In this paper, we present an efficiency improvement for the algorithm called AMOEBA, A Multidirectional Optimum Ecotope-Based Algorithm, devised by Aldstadt and Getis (Geogr Anal 38(4):327343, 2006). AMOEBA embeds a local spatial autocorrelation statistic in an iterative procedure in order to identify spatial clusters (ecotopes) of related spatial units. We provide an analysis of the computational complexity of the original AMOEBA and develop an alternative formulation that reduces computational time without losing optimality. Empirical evidence is provided using georeferenced socio-demographic data in Accra, Ghana.
Keywords AMOEBA - Cluster detection - Local G statistic - Ecotope
JEL Classification C02 mathematical methods - C4 econometric and statistical methods: special topics
HouSI: A heuristic for the delimitation of housing submarkets and price homogeneous areas
Python library with spatially constrained clustering algorithms
Interactive tool for visualizing the interindustry dynamics in Colombian economy.
The Center for Urban and Environmental Studies, Urbam, is a new RiSE's partner. Interesting projects are coming!
Doctor Xinyue Ye, a RiSE’s academic affiliate, was awarded the Regional Development and Planning (RDPSG) Emerging Scholar by the Association of American Geographers (AAG).
The VI World Conference of the Spatial Econometrics Association (SEA) Conference in Latin America
